Jeff Clune
@jeffclune.com
Professor, Computer Science, University of British Columbia. CIFAR AI Chair, Vector Institute. Senior Advisor, DeepMind. ML, AI, deep RL, deep learning, AI-Generating Algorithms (AI-GAs), open-endedness.
Reposted by Jeff Clune
For all the details, please give the paper a read!
Paper: arxiv.org/abs/2507.06466
Infinite thanks to @jeffclune.com and @cong-ml.bsky.social for all their guidance!
Paper: arxiv.org/abs/2507.06466
Infinite thanks to @jeffclune.com and @cong-ml.bsky.social for all their guidance!
Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models
Multi-agent interactions have long fueled innovation, from natural predator-prey dynamics to the space race. Self-play (SP) algorithms try to harness these dynamics by pitting agents against ever-impr...
arxiv.org
July 10, 2025 at 6:17 PM
For all the details, please give the paper a read!
Paper: arxiv.org/abs/2507.06466
Infinite thanks to @jeffclune.com and @cong-ml.bsky.social for all their guidance!
Paper: arxiv.org/abs/2507.06466
Infinite thanks to @jeffclune.com and @cong-ml.bsky.social for all their guidance!
Note: This is not a fundamental dismissal of deep learning. In fact, we have worked improving and leveraging deep learning for years, and are optimistic about its present and future. These results point to a way it could be substantially improved, which is exciting.
May 20, 2025 at 6:23 PM
Note: This is not a fundamental dismissal of deep learning. In fact, we have worked improving and leveraging deep learning for years, and are optimistic about its present and future. These results point to a way it could be substantially improved, which is exciting.
Great work AlphaEvolve team!
MAP-Elites co-authored with Jean-Baptiste Mouret
MAP-Elites co-authored with Jean-Baptiste Mouret
May 14, 2025 at 4:53 PM
Great work AlphaEvolve team!
MAP-Elites co-authored with Jean-Baptiste Mouret
MAP-Elites co-authored with Jean-Baptiste Mouret